pianyushi / fedtrack

A Collaborative Target Tracking Framework based on Adaptive Federated Learning

FedTrack

Environment

• pyqmdnet.yaml

• pysot-tookit/requirements.txt

Introduction

PyTorch implementation of FedTrack, which runs with a single CPU core and a single GPU (GTX 3080 Ti).

Datasets

• training datasets: Imagenet-VID and vot2018\19\21

• testing datasets: OTB100, LaSOT, GOT-10k

Results on OTB

Prerequisites

• python 3.9+

• opencv 4.6+

• PyTorch 2.0+ and its dependencies

• for GPU support: a GPU with ~4G memory

Usage

Co-Tracking Training

 python pretrain/fedtrain.py

Evaluation

• Visualization of the trace

   python tracking/run_tracker.py -s Basketball [-d (display fig)] [-f (save fig)]
  

  • You can provide a sequence configuration in two ways (see tracking/gen_config.py):

    • python tracking/run_tracker.py -s [seq name]

    • python tracking/run_tracker.py -j [json path]

• Draw success and precision

   python pysot-tookit/pysot/visualization/draw_success_precision.py

• Pretraining on ImageNet-VID

  • Download ImageNet-VID dataset into "datasets/ILSVRC"

   python pretrain/prepro_imagenet.py
   python pretrain/train_mdnet.py -d imagenet